The present work presents a methodology based on data reconciliation to monitor membrane separation processes reliably, online and in real time for the first time. The proposed methodology was implemented in accordance with the following steps: data acquisition; data pre-treatment; data characterization; data reconciliation; gross error detection; and critical evaluation of measured data with a soft sensor. The acquisition of data constituted the slowest stage of the monitoring process, as expected in real-time applications. The pre-treatment stage was fundamental to assure the robustness of the code and the initial characterization of collected data was carried out offline. The characterization of the data showed that steady-state modeling of the process would be appropriate, also allowing the implementation of faster numerical procedures for the data reconciliation step. The data reconciliation step performed well, quickly and consistently. Thus, data reconciliation allowed the estimation of unmeasured variables, playing the role of a soft sensor and allowing the future installation of a digital twin. Additionally, monitoring of measurement bias constituted a tool for measurement diagnosis. As shown in the manuscript, the proposed methodology can be successfully implemented online and in real time for monitoring of membrane separation processes, as shown through a real dashboard web application developed for monitoring of an actual industrial site.

The present study presents, for the first time, the real-time monitoring of an actual spiral-wound membrane unit used for ${\mathrm{CO}}_2$ removal from natural gas in an actual industrial offshore platform, utilizing a detailed phenomenological model. An Object-Oriented Programming (OOP) paradigm was employed to simulate the offshore membrane separation unit, accounting for the diverse levels of the membrane separation setup. A parameter estimation procedure was implemented to fit the phenomenological model to the real industrial data in real-time, for the first time. In addition, estimated permeance parameters and calculated unmeasured variables (soft sensor) were used for monitoring Key Performance Indicators (KPIs), such as membrane selectivity, dew point temperature, and hydrocarbon loss. Finally, a reparametrization of the parameters was implemented to improve the robustness of the optimization procedure. Thus, the model variables presented good adjustments to the data, indicating the satisfactory performance of the estimation. Consequently, the good accuracy of the model provided reliable information to the soft sensors and KPIs.